AMD EPYC Benchmarks With Intel Xeon Whitepaper Recommended Benchmarks

Xeon Plat Off-Roadmap 8124M Comparison

HTML result view exported from: https://openbenchmarking.org/result/2007297-AS-2005266AS56&grs&sro.

AMD EPYC Benchmarks With Intel Xeon Whitepaper Recommended BenchmarksProcessorMotherboardChipsetMemoryDiskGraphicsNetworkMonitorOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionEPYC 7601 2PXeon Platinum 8280 2PEPYC 7642 2PEPYC 7742 2PXeon Gold 6254 2xXeon Plat 8124M2 x AMD EPYC 7601 32-Core (64 Cores / 128 Threads)Dell 02MJ3T (1.2.5 BIOS)AMD 17h516096MB280GB INTEL SSDPED1D280GAllvmpipe 504GB2 x Broadcom BCM57416 NetXtreme-E Dual-Media 10G RDMA + 2 x Broadcom NetXtreme BCM5720 2-port PCIeUbuntu 19.105.3.0-19-generic (x86_64)GNOME Shell 3.34.1X Server 1.20.5modesetting 1.20.53.3 Mesa 19.2.1 (LLVM 9.0 128 bits)GCC 9.2.1 20191008ext41600x12002 x Intel Xeon Platinum 8280 @ 4.00GHz (56 Cores / 112 Threads)GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS)Intel Sky Lake-E DMI3 Registers386048MBllvmpipe 377GB2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE5.3.0-18-generic (x86_64)3.3 Mesa 19.2.1 (LLVM 9.0 256 bits)1920x10802 x AMD EPYC 7642 48-Core @ 2.30GHz (96 Cores / 192 Threads)AMD DAYTONA_X (RDY1001C BIOS)AMD Starship/Matisse516096MBllvmpipe 504GB2 x Mellanox MT277103.3 Mesa 19.2.1 (LLVM 9.0 128 bits)2 x AMD EPYC 7742 64-Core @ 2.25GHz (128 Cores / 256 Threads)2 x Intel Xeon Gold 6254 @ 4.00GHz (36 Cores / 72 Threads)GIGABYTE MR91-FS0-00 v01000100 (R08 BIOS)Intel Sky Lake-E DMI3 Registers773120MB4 x 400GB KXG50ZNV512G TOSHIBAASPEEDDELL U2412M2 x Intel I350Fedora 305.3.8-200.local.fc30.x86_64 (x86_64)GNOME Shell 3.32.2GCC 9.2.1 201908271920x12002 x Intel Xeon Platinum 8124M @ 3.50GHz (36 Cores / 72 Threads)96256MB4 x 400GB KXG50ZNV512G TOSHIBA + 128GB SAMSUNG SSD SM84llvmpipe 93GB289K2 x Intel I350 + 2 x Intel 10-Gigabit X540-AT2Fedora 325.6.14-300.fc32.x86_64 (x86_64)GNOME Shell 3.36.2X Server 1.20.8 + Waylandmodesetting 1.20.83.3 Mesa 20.0.7 (LLVM 10.0.0 256 bits)GCC 10.1.1 20200507 + Clang 10.0.0OpenBenchmarking.orgCompiler Details- EPYC 7601 2P: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Xeon Platinum 8280 2P: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - EPYC 7642 2P: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - EPYC 7742 2P: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Xeon Gold 6254 2x: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,objc,obj-c++,ada,go,d,lto --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=i686 --with-gcc-major-version-only --with-isl --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver- Xeon Plat 8124M: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,objc,obj-c++,ada,go,d,lto --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=i686 --with-gcc-major-version-only --with-isl --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driverJava Details- EPYC 7601 2P, Xeon Platinum 8280 2P, EPYC 7642 2P, EPYC 7742 2P: OpenJDK Runtime Environment (build 11.0.5-ea+10-post-Ubuntu-0ubuntu1)Security Details- EPYC 7601 2P: l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: disabled RSB filling- Xeon Platinum 8280 2P: l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling- EPYC 7642 2P: l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling- EPYC 7742 2P: l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling- Xeon Gold 6254 2x: SELinux + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling- Xeon Plat 8124M: SELinux + itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + tsx_async_abort: Mitigation of Clear buffers; SMT vulnerableProcessor Details- Xeon Platinum 8280 2P: Scaling Governor: intel_pstate powersave- EPYC 7642 2P: Scaling Governor: acpi-cpufreq ondemand- EPYC 7742 2P: Scaling Governor: acpi-cpufreq ondemand- Xeon Gold 6254 2x: Scaling Governor: intel_pstate performance- Xeon Plat 8124M: Scaling Governor: intel_pstate powersave

AMD EPYC Benchmarks With Intel Xeon Whitepaper Recommended Benchmarksmt-dgemm: Sustained Floating-Point Ratehpcc: G-HPLhpcc: G-Ffteembree: Pathtracer - Crownembree: Pathtracer ISPC - Crownhmmer: Pfam Database Searchembree: Pathtracer ISPC - Asian Dragon Objembree: Pathtracer ISPC - Asian Dragonembree: Pathtracer - Asian Dragon Objembree: Pathtracer - Asian Dragonhpcc: EP-DGEMMnamd: ATPase Simulation - 327,506 Atomsspec-jbb2015: SPECjbb2015-Composite critical-jOPSstream: Triadstream: Addspec-jbb2015: SPECjbb2015-Composite max-jOPSstream: Scalestream: Copyaskap: tConvolve MPI - Griddingaskap: tConvolve MPI - Degriddinghpcc: G-Ffteaskap: tConvolve MT - Degriddingaskap: tConvolve MT - Griddingminife: SmallEPYC 7601 2PXeon Platinum 8280 2PEPYC 7642 2PEPYC 7742 2PXeon Gold 6254 2xXeon Plat 8124M4.55196.9760027.2760027.6826.346.3722.8227.5622.0828.1916.787700.4501631561178352.60178494.7265302157903.12158117.208154.5910755.576153.922535.336735.3220.16147.0060016.8625045.9452.7511.2458.8268.6051.4656.8727.250400.3618452414155420.80159582.0693162145075.94162606.806817.779661.136201.323921.7313908.5720.04220.6670032.1911069.0765.556.4648.4156.4951.6658.8322.459100.3068753036188072.88187929.1091951164704.96180668.529440.0812782.606760.704541.7815476.7528.69298.7420049.1856083.2477.557.0248.7957.2051.6959.3720.697300.2608258949197250.06191550.10106645174281.36181951.609481.8012184.876555.794568.9314994.8814.703.970.50229143738.42143492.92129431.66165319.885682.743213.2812.5650.6358715.1883335.7939.924.4142.2748.8836.3539.851.515350.50224116929.56116527.98106752.80130589.5215.188335284.923217.74OpenBenchmarking.org

ACES DGEMM

Sustained Floating-Point Rate

OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Gold 6254 2xXeon Plat 8124MXeon Platinum 8280 2P714212835SE +/- 0.06, N = 4SE +/- 0.10, N = 3SE +/- 0.43, N = 12SE +/- 0.12, N = 3SE +/- 0.19, N = 3SE +/- 0.12, N = 34.5520.0428.6914.7012.5620.161. (CC) gcc options: -O3 -march=native -fopenmp

HPC Challenge

Test / Class: G-HPL

OpenBenchmarking.orgGFLOPS, More Is BetterHPC Challenge 1.5.0Test / Class: G-HPLEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Plat 8124MXeon Platinum 8280 2P70140210280350SE +/- 0.00, N = 3196.98220.67298.7450.64147.011. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. EPYC 7601 2P: OpenBLAS + Open MPI 3.1.33. EPYC 7642 2P: OpenBLAS + Open MPI 3.1.34. EPYC 7742 2P: OpenBLAS + Open MPI 3.1.35. Xeon Plat 8124M: ATLAS + Open MPI 4.0.36. Xeon Platinum 8280 2P: OpenBLAS + Open MPI 3.1.3

Timed HMMer Search

Performance / Cost - Pfam Database Search

OpenBenchmarking.orgSeconds x Dollar, Fewer Is BetterTimed HMMer Search 2.3.2Performance / Cost - Pfam Database SearchEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Platinum 8280 2P50K100K150K200K250K40768.0069884.28105608.88225002.321. EPYC 7601 2P: $6400 reported cost.2. EPYC 7642 2P: $10818 reported cost.3. EPYC 7742 2P: $15044 reported cost.4. Xeon Platinum 8280 2P: $20018 reported cost.

ASKAP

Performance / Cost - Test: tConvolve MPI - Gridding

OpenBenchmarking.orgMillion Grid Points Per Second Per Dollar, More Is BetterASKAP 2018-11-10Performance / Cost - Test: tConvolve MPI - GriddingEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Platinum 8280 2P0.28580.57160.85741.14321.4291.270.870.630.341. EPYC 7601 2P: $6400 reported cost.2. EPYC 7642 2P: $10818 reported cost.3. EPYC 7742 2P: $15044 reported cost.4. Xeon Platinum 8280 2P: $20018 reported cost.

Stream

Performance / Cost - Type: Triad

OpenBenchmarking.orgMB/s Per Dollar, More Is BetterStream 2013-01-17Performance / Cost - Type: TriadEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Platinum 8280 2P71421283527.8717.3913.117.761. EPYC 7601 2P: $6400 reported cost.2. EPYC 7642 2P: $10818 reported cost.3. EPYC 7742 2P: $15044 reported cost.4. Xeon Platinum 8280 2P: $20018 reported cost.

ASKAP

Performance / Cost - Test: tConvolve MPI - Degridding

OpenBenchmarking.orgMillion Grid Points Per Second Per Dollar, More Is BetterASKAP 2018-11-10Performance / Cost - Test: tConvolve MPI - DegriddingEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Platinum 8280 2P0.3780.7561.1341.5121.891.681.180.810.481. EPYC 7601 2P: $6400 reported cost.2. EPYC 7642 2P: $10818 reported cost.3. EPYC 7742 2P: $15044 reported cost.4. Xeon Platinum 8280 2P: $20018 reported cost.

Stream

Performance / Cost - Type: Add

OpenBenchmarking.orgMB/s Per Dollar, More Is BetterStream 2013-01-17Performance / Cost - Type: AddEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Platinum 8280 2P71421283527.8917.3712.737.971. EPYC 7601 2P: $6400 reported cost.2. EPYC 7642 2P: $10818 reported cost.3. EPYC 7742 2P: $15044 reported cost.4. Xeon Platinum 8280 2P: $20018 reported cost.

Stream

Performance / Cost - Type: Scale

OpenBenchmarking.orgMB/s Per Dollar, More Is BetterStream 2013-01-17Performance / Cost - Type: ScaleEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Platinum 8280 2P61218243024.6715.2311.587.251. EPYC 7601 2P: $6400 reported cost.2. EPYC 7642 2P: $10818 reported cost.3. EPYC 7742 2P: $15044 reported cost.4. Xeon Platinum 8280 2P: $20018 reported cost.

HPC Challenge

Test / Class: G-Ffte

OpenBenchmarking.orgGFLOPS, More Is BetterHPC Challenge 1.5.0Test / Class: G-FfteEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Plat 8124MXeon Platinum 8280 2P1122334455SE +/- 0.07, N = 327.2832.1949.1915.1916.861. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. EPYC 7601 2P: OpenBLAS + Open MPI 3.1.33. EPYC 7642 2P: OpenBLAS + Open MPI 3.1.34. EPYC 7742 2P: OpenBLAS + Open MPI 3.1.35. Xeon Plat 8124M: ATLAS + Open MPI 4.0.36. Xeon Platinum 8280 2P: OpenBLAS + Open MPI 3.1.3

ASKAP

Performance / Cost - Test: tConvolve MT - Degridding

OpenBenchmarking.orgMillion Grid Points Per Second Per Dollar, More Is BetterASKAP 2018-11-10Performance / Cost - Test: tConvolve MT - DegriddingEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Platinum 8280 2P0.2160.4320.6480.8641.080.960.620.440.311. EPYC 7601 2P: $6400 reported cost.2. EPYC 7642 2P: $10818 reported cost.3. EPYC 7742 2P: $15044 reported cost.4. Xeon Platinum 8280 2P: $20018 reported cost.

Stream

Performance / Cost - Type: Copy

OpenBenchmarking.orgMB/s Per Dollar, More Is BetterStream 2013-01-17Performance / Cost - Type: CopyEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Platinum 8280 2P61218243024.7116.7012.098.121. EPYC 7601 2P: $6400 reported cost.2. EPYC 7642 2P: $10818 reported cost.3. EPYC 7742 2P: $15044 reported cost.4. Xeon Platinum 8280 2P: $20018 reported cost.

Embree

Binary: Pathtracer - Model: Crown

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer - Model: CrownEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Plat 8124MXeon Platinum 8280 2P20406080100SE +/- 0.07, N = 3SE +/- 0.12, N = 3SE +/- 0.62, N = 3SE +/- 0.06, N = 3SE +/- 0.14, N = 327.6869.0783.2435.7945.94MIN: 27.18 / MAX: 28.74MIN: 65.92 / MAX: 73.22MIN: 74.54 / MAX: 90.77MIN: 35.09 / MAX: 36.51MIN: 44.35 / MAX: 47.68

HPC Challenge

Performance / Cost - Test / Class: G-HPL

OpenBenchmarking.orgGFLOPS Per Dollar, More Is BetterHPC Challenge 1.5.0Performance / Cost - Test / Class: G-HPLEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Platinum 8280 2P0.00680.01360.02040.02720.0340.030.020.020.011. EPYC 7601 2P: $6400 reported cost.2. EPYC 7642 2P: $10818 reported cost.3. EPYC 7742 2P: $15044 reported cost.4. Xeon Platinum 8280 2P: $20018 reported cost.

Embree

Binary: Pathtracer ISPC - Model: Crown

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer ISPC - Model: CrownEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Plat 8124MXeon Platinum 8280 2P20406080100SE +/- 0.09, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.47, N = 326.3465.5577.5539.9252.75MIN: 25.81 / MAX: 27.61MIN: 62.83 / MAX: 69.45MIN: 72.12 / MAX: 85.47MIN: 39.07 / MAX: 41.14MIN: 49.21 / MAX: 55.87

Timed HMMer Search

Pfam Database Search

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 2.3.2Pfam Database SearchEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Gold 6254 2xXeon Plat 8124MXeon Platinum 8280 2P3691215SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.09, N = 3SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.12, N = 36.376.467.023.974.4111.241. (CC) gcc options: -O2 -pthread -lhmmer -lsquid -lm

Embree

Binary: Pathtracer ISPC - Model: Asian Dragon Obj

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer ISPC - Model: Asian Dragon ObjEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Plat 8124MXeon Platinum 8280 2P1326395265SE +/- 0.29, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.06, N = 3SE +/- 0.08, N = 322.8248.4148.7942.2758.82MIN: 22.09 / MAX: 23.73MIN: 46.93 / MAX: 51.2MIN: 46.07 / MAX: 52.01MIN: 41.69 / MAX: 43.08MIN: 57.06 / MAX: 60.8

NAMD

Performance / Cost - ATPase Simulation - 327,506 Atoms

OpenBenchmarking.orgdays/ns x Dollar, Fewer Is BetterNAMD 2.13b1Performance / Cost - ATPase Simulation - 327,506 AtomsEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Platinum 8280 2P160032004800640080002881.023319.723923.787243.311. EPYC 7601 2P: $6400 reported cost.2. EPYC 7642 2P: $10818 reported cost.3. EPYC 7742 2P: $15044 reported cost.4. Xeon Platinum 8280 2P: $20018 reported cost.

Embree

Binary: Pathtracer ISPC - Model: Asian Dragon

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer ISPC - Model: Asian DragonEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Plat 8124MXeon Platinum 8280 2P1530456075SE +/- 0.06, N = 3SE +/- 0.21, N = 3SE +/- 0.16, N = 3SE +/- 0.25, N = 3SE +/- 0.09, N = 327.5656.4957.2048.8868.60MIN: 27.14 / MAX: 28.29MIN: 54.38 / MAX: 59.7MIN: 53.96 / MAX: 60.24MIN: 46.68 / MAX: 50.2MIN: 66.53 / MAX: 70.6

Embree

Binary: Pathtracer - Model: Asian Dragon Obj

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer - Model: Asian Dragon ObjEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Plat 8124MXeon Platinum 8280 2P1224364860SE +/- 0.25, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.27, N = 322.0851.6651.6936.3551.46MIN: 21.52 / MAX: 22.97MIN: 49.83 / MAX: 54.59MIN: 49.03 / MAX: 54.82MIN: 35.97 / MAX: 36.87MIN: 49.92 / MAX: 53.03

SPECjbb 2015

Performance / Cost - SPECjbb2015-Composite max-jOPS

OpenBenchmarking.orgjOPS Per Dollar, More Is BetterSPECjbb 2015Performance / Cost - SPECjbb2015-Composite max-jOPSEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Platinum 8280 2P369121510.208.507.094.651. EPYC 7601 2P: $6400 reported cost.2. EPYC 7642 2P: $10818 reported cost.3. EPYC 7742 2P: $15044 reported cost.4. Xeon Platinum 8280 2P: $20018 reported cost.

Embree

Binary: Pathtracer - Model: Asian Dragon

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer - Model: Asian DragonEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Plat 8124MXeon Platinum 8280 2P1326395265SE +/- 0.02, N = 3SE +/- 0.25, N = 3SE +/- 0.08, N = 3SE +/- 0.37, N = 3SE +/- 0.21, N = 328.1958.8359.3739.8556.87MIN: 27.9 / MAX: 28.87MIN: 56.61 / MAX: 62.02MIN: 56.29 / MAX: 62.09MIN: 38.3 / MAX: 40.84MIN: 55.31 / MAX: 58.68

ASKAP

Performance / Cost - Test: tConvolve MT - Gridding

OpenBenchmarking.orgMillion Grid Points Per Second Per Dollar, More Is BetterASKAP 2018-11-10Performance / Cost - Test: tConvolve MT - GriddingEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Platinum 8280 2P0.09450.1890.28350.3780.47250.400.420.300.201. EPYC 7601 2P: $6400 reported cost.2. EPYC 7642 2P: $10818 reported cost.3. EPYC 7742 2P: $15044 reported cost.4. Xeon Platinum 8280 2P: $20018 reported cost.

miniFE

Performance / Cost - Problem Size: Small

OpenBenchmarking.orgCG Mflops Per Dollar, More Is BetterminiFE 2.2Performance / Cost - Problem Size: SmallEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Platinum 8280 2P0.32180.64360.96541.28721.6091.051.431.000.691. EPYC 7601 2P: $6400 reported cost.2. EPYC 7642 2P: $10818 reported cost.3. EPYC 7742 2P: $15044 reported cost.4. Xeon Platinum 8280 2P: $20018 reported cost.

HPC Challenge

Test / Class: EP-DGEMM

OpenBenchmarking.orgGFLOPS, More Is BetterHPC Challenge 1.5.0Test / Class: EP-DGEMMEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Plat 8124MXeon Platinum 8280 2P612182430SE +/- 0.00109, N = 316.7877022.4591020.697301.5153527.250401. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. EPYC 7601 2P: OpenBLAS + Open MPI 3.1.33. EPYC 7642 2P: OpenBLAS + Open MPI 3.1.34. EPYC 7742 2P: OpenBLAS + Open MPI 3.1.35. Xeon Plat 8124M: ATLAS + Open MPI 4.0.36. Xeon Platinum 8280 2P: OpenBLAS + Open MPI 3.1.3

NAMD

ATPase Simulation - 327,506 Atoms

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.13b1ATPase Simulation - 327,506 AtomsEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Gold 6254 2xXeon Plat 8124MXeon Platinum 8280 2P0.1130.2260.3390.4520.565SE +/- 0.00039, N = 12SE +/- 0.00192, N = 3SE +/- 0.00322, N = 4SE +/- 0.00436, N = 3SE +/- 0.00346, N = 3SE +/- 0.00055, N = 70.450160.306870.260820.502290.502240.36184

SPECjbb 2015

Performance / Cost - SPECjbb2015-Composite critical-jOPS

OpenBenchmarking.orgjOPS Per Dollar, More Is BetterSPECjbb 2015Performance / Cost - SPECjbb2015-Composite critical-jOPSEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Platinum 8280 2P1.10932.21863.32794.43725.54654.934.903.922.621. EPYC 7601 2P: $6400 reported cost.2. EPYC 7642 2P: $10818 reported cost.3. EPYC 7742 2P: $15044 reported cost.4. Xeon Platinum 8280 2P: $20018 reported cost.

SPECjbb 2015

SPECjbb2015-Composite critical-jOPS

OpenBenchmarking.orgjOPS, More Is BetterSPECjbb 2015SPECjbb2015-Composite critical-jOPSEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Platinum 8280 2P13K26K39K52K65K31561530365894952414

Stream

Type: Triad

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: TriadEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Gold 6254 2xXeon Plat 8124MXeon Platinum 8280 2P40K80K120K160K200KSE +/- 1850.63, N = 5SE +/- 4363.98, N = 5SE +/- 920.61, N = 5SE +/- 2813.49, N = 5SE +/- 175.01, N = 5SE +/- 6150.28, N = 5178352.60188072.88197250.06143738.42116929.56155420.801. (CC) gcc options: -O3 -march=native -fopenmp

Stream

Type: Add

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: AddEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Gold 6254 2xXeon Plat 8124MXeon Platinum 8280 2P40K80K120K160K200KSE +/- 976.05, N = 5SE +/- 881.24, N = 5SE +/- 776.21, N = 5SE +/- 2479.78, N = 5SE +/- 187.36, N = 5SE +/- 3139.44, N = 5178494.72187929.10191550.10143492.92116527.98159582.061. (CC) gcc options: -O3 -march=native -fopenmp

SPECjbb 2015

SPECjbb2015-Composite max-jOPS

OpenBenchmarking.orgjOPS, More Is BetterSPECjbb 2015SPECjbb2015-Composite max-jOPSEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Platinum 8280 2P20K40K60K80K100K653029195110664593162

Stream

Type: Scale

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: ScaleEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Gold 6254 2xXeon Plat 8124MXeon Platinum 8280 2P40K80K120K160K200KSE +/- 1398.05, N = 5SE +/- 1737.04, N = 5SE +/- 1498.12, N = 5SE +/- 1742.69, N = 5SE +/- 923.01, N = 5SE +/- 570.53, N = 5157903.12164704.96174281.36129431.66106752.80145075.941. (CC) gcc options: -O3 -march=native -fopenmp

Stream

Type: Copy

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: CopyEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Gold 6254 2xXeon Plat 8124MXeon Platinum 8280 2P40K80K120K160K200KSE +/- 1259.52, N = 5SE +/- 1825.81, N = 5SE +/- 895.82, N = 5SE +/- 2391.31, N = 25SE +/- 1111.52, N = 5SE +/- 3742.53, N = 25158117.20180668.52181951.60165319.88130589.52162606.801. (CC) gcc options: -O3 -march=native -fopenmp

ASKAP

Test: tConvolve MPI - Gridding

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 2018-11-10Test: tConvolve MPI - GriddingEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Platinum 8280 2P2K4K6K8K10KSE +/- 1.30, N = 3SE +/- 4.19, N = 3SE +/- 0.88, N = 3SE +/- 14.26, N = 38154.599440.089481.806817.771. (CXX) g++ options: -lpthread

ASKAP

Test: tConvolve MPI - Degridding

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 2018-11-10Test: tConvolve MPI - DegriddingEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Platinum 8280 2P3K6K9K12K15KSE +/- 5.97, N = 3SE +/- 33.51, N = 3SE +/- 24.05, N = 3SE +/- 4.18, N = 310755.5712782.6012184.879661.131. (CXX) g++ options: -lpthread

HPC Challenge

Test / Class: G-Ffte

OpenBenchmarking.orgGFLOP/s, More Is BetterHPC Challenge 1.5.0Test / Class: G-FfteXeon Plat 8124M48121620SE +/- 0.07, N = 315.191. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 4.0.3

ASKAP

Test: tConvolve MT - Degridding

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 2018-11-10Test: tConvolve MT - DegriddingEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Gold 6254 2xXeon Plat 8124MXeon Platinum 8280 2P14002800420056007000SE +/- 117.38, N = 12SE +/- 142.23, N = 12SE +/- 127.68, N = 9SE +/- 116.26, N = 15SE +/- 167.05, N = 15SE +/- 185.60, N = 126153.926760.706555.795682.745284.926201.321. (CXX) g++ options: -lpthread

ASKAP

Test: tConvolve MT - Gridding

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 2018-11-10Test: tConvolve MT - GriddingEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Gold 6254 2xXeon Plat 8124MXeon Platinum 8280 2P10002000300040005000SE +/- 124.64, N = 12SE +/- 59.27, N = 12SE +/- 57.87, N = 9SE +/- 50.84, N = 15SE +/- 101.77, N = 15SE +/- 114.58, N = 122535.334541.784568.933213.283217.743921.731. (CXX) g++ options: -lpthread

miniFE

Problem Size: Small

OpenBenchmarking.orgCG Mflops, More Is BetterminiFE 2.2Problem Size: SmallEPYC 7601 2PEPYC 7642 2PEPYC 7742 2PXeon Platinum 8280 2P3K6K9K12K15KSE +/- 65.81, N = 3SE +/- 452.97, N = 15SE +/- 280.05, N = 15SE +/- 642.73, N = 126735.3215476.7514994.8813908.571. (CXX) g++ options: -O3 -fopenmp -pthread -lmpi_cxx -lmpi

Phoronix Test Suite v10.8.5